HyperAI
Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
3,295 papers
Physical Words: A Vocabulary for Structuring Latent Reasoning in Robot Manipulation
World Models
Multimodal Representation
Jiaming Liu, Xinghao Zhu, Yiming Zhang, et al.
Latent Reasoning in Continuous Space for Unified Multimodal Models
Any-to-Any
Text-to-Image
Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, et al.
HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model
World Models
Multimodal
Rongxing Ding, Hongyu Qu, Kehong Wu, et al.
Wizard: An Agentic Game World Model
World Models
Agent
Yuzhe Wu, Zijun Lin, Yeying Jin
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
Image Generation
Image-to-Image
Yijing Lin, Zhendong Mao, Mengqi Huang, et al.
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
Reasoning
LLM
Qi Wang, Yun Qu, Lizhou Cai, et al.
R2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
Agent
Reinforcement Learning
Mingda Zhang, Yun Huang, Qiang Huang, et al.
A Broader Look into MLLM’s Retrieval Heads
Multimodal
Visual Document Retrieval
Jia Wang, Yuqing Li, Jiangnan Li, et al.
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
Agent
Supervised Fine-Tuning
Ziyang Zeng, Tingyang Chen, Jia Deng, et al.
L3G-WORLD: REAL-TIME INFINITE WORLD GENERATION WITH LATENT 3D GAUSSIAN MEMORY
World Models
Diffusion Model
Jinhyeok Choi, JoungBin Lee, Jongmin Lee, et al.
Proving and Improving the Platonic Representation Hypothesis with JEPAs
Multimodal Representation
Image Captioning
Randall Balestriero, Yann LeCun
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
Model Training
Multimodal
Yu Liu, Youxing Li, Yuedong Tan, et al.
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
Diffusion Model
Multimodal
Donghyeon Cho, Joowon Kim, Seungho Shin, et al.
REALCLI: TOWARD A UNIFIED EVALUATION OF HUMAN–AGENT COLLABORATION FOR CLI AGENTS
Agent
Benchmarks
Yunqi Liu, Peiyu Wang, Bingli Wang, et al.
TAO: TOOL-AWARE JOINT SCHEDULING FOR LLM-BASED AGENTIC SERVING
LLM
Agent
Shuhuai Li, Dongdong Ge, Yinyu Ye, et al.
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
Embodied Intelligence
Multimodal Representation
Yunfei Xie, Howard H. Qian, Shiyi Lan, et al.
OMNISHOWCASE: OMNIDIRECTIONAL SUBJECT-CONSISTENT VIDEO GENERATION FROM MULTI-VIEWIMAGES
Image-to-Video
Video Generation
Junyeong Ahn, Geonwoo Kim, Kinam Kim, et al.
Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
Audio and Speech Processing
Multimodal Representation
Wendi Sang, Kai Li, Yifan Li, et al.
DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models
Reinforcement Learning
Diffusion Model
Hongze Chen, Miao Pan, Lizhou Liang, et al.
CodeCap-Bench: Can Code Serve as a Good Video Caption?
Video Captioning
Code Generation
Jiafu Tang, Yifan Xu, Eric Tang, et al.
Rollback: Experience Backtracking in World Models for Policy Improvement
World Models
Reinforcement Learning
Jiayi Luo, Yang Zhang, Liliang Chen, et al.
The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents
Agent
Multimodal
Weidong Tang, Ruiheng Wang, Jingxuan Zhang, et al.
PDRVLA: A VISION–LANGUAGE–ACTION MODEL WITH PHYSICAL DYNAMICS REPRESENTATIONS
Multimodal Representation
World Models
Hanqing Wang, Zhaotian Cai, Ruichuan An, et al.
Hy-Nomas: Towards Free-form Interactive World Generation
World Models
Diffusion Model
Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng, et al.
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Supervised Fine-Tuning
Video Understanding
Yihao Hu, Yitong Lin, Pan Wang, et al.
Are Self-Evolving Agents Continual Learners?
Agent
LLM
Xiaoyin Chen, Yizheng Huang, Yinglun Xu, et al.
Work Agents: Systems, Capabilities, and Optimization
Agent
LLM
Zishan Xu, Enjun Du, Mingqi Gao, et al.
InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
Multimodal
Agent
Qinsi Wang, Wei Wen, Chong Zhou, et al.
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
Benchmarks
Agent
Zhiyong Cao, Hengjie Zhu, Yongxin Wang, et al.
DynaFlow: Learning Free-Form Multi-Agent Orchestration
Agent
Code Generation
Ruhao Liu, Qi Li, Shizun Wang, et al.